US11663707B2ActiveUtilityA1

Method and system for image enhancement

73
Assignee: UNIV CHONGQING POSTS & TELECOMPriority: Apr 14, 2015Filed: Mar 28, 2022Granted: May 30, 2023
Est. expiryApr 14, 2035(~8.8 yrs left)· nominal 20-yr term from priority
G06T 2207/20076G06T 5/10G06T 5/50G06T 2207/30168H04N 1/6005G06T 5/40G06T 2207/10024G06T 5/009G06T 5/92
73
PatentIndex Score
0
Cited by
31
References
20
Claims

Abstract

A method for image processing, which comprises the following steps: Generating a first histogram from a first image; Calculating a first parameter profile from the first image indicative of the quality of the first image; Adjusting the first parameter profile to generate a second parameter profile; Using the second parameter profile to generate a statistical distribution via a statistical distribution generator, wherein the statistical distribution is characterized by at least three parameters; Using the statistical distribution to perform a histogram specification to the first histogram of the first image to generate a second histogram; Generating a second image based on the first image and the second histogram.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
       1. A method for image processing, which comprises the following steps:
 generating a first histogram from a first image; 
 calculating a first parameter profile from the first image indicative of the quality of the first image by using an inverse cloud generator; 
 adjusting the first parameter profile to generate a second parameter profile based on the first histogram; 
 using a cloud generator to generate a second statistical distribution based on the second parameter profile; 
 generating a second histogram based on the second statistical distribution; generating a second image based on the first image and the second histogram. 
 
     
     
       2. The method of  claim 1 , wherein the cloud generator comprises multiple random number generators (RNGs) and multiple buffers, the RNGs generate random variables with Gaussian distribution, and the multiple buffers store the intermediate random values generated by the RNGs. 
     
     
       3. The method of  claim 1 , further including:
 using the first parameter profile as an input to the inverse cloud generator to generate a first statistical distribution; and 
 using the first distribution to perform the histogram specification to the first histogram of the first image. 
 
     
     
       4. The method of  claim 1 , further including:
 using the second parameter profile as an input to the cloud generator to generate the second statistical distribution. 
 
     
     
       5. The method of  claim 1 , the calculating the first parameter profile from the first image further comprises:
 reading the first image and storing intensity information for each pixel of the first image; and 
 calculating the first parameter profile according to the stored intensity information. 
 
     
     
       6. The method of  claim 5 , wherein the intensity information includes at least one of RGB values in a RGB format image, Y-component values in a YUV format image, or grey level values in a grayscale image. 
     
     
       7. The method of  claim 1 , wherein the parameter profile includes at least one of an average luminance of the first image, brightness of the first image, or a contrast of the first image. 
     
     
       8. The method of  claim 3 , wherein generating the first statistical distribution based on the first parameter profile further comprises:
 transferring the first parameter profile to the cloud generator; and 
 generating the first statistical distribution via the cloud generator mapping at least three parameters selected from the first parameter profile. 
 
     
     
       9. The method of  claim 8 , wherein the at least three parameters selected from the first parameter profile comprise expectation, entropy and hyper entropy. 
     
     
       10. The method of  claim 3 , wherein the generating the second parameter profile is performed by adjusting the first parameter profile with an iterative algorithm. 
     
     
       11. An image processing system comprising:
 a computing unit, adapted to:
 generate a first histogram from a first image; and 
 calculate a first parameter profile from the first image indicative of the quality of the first image by using an inverse cloud generator; 
 
 an adjustment unit, adapted to:
 adjust the first parameter profile to generate a second parameter profile based on the first histogram; 
 
 a specification unit, adapted to:
 use a cloud generator to generate a second statistical distribution based on the second parameter profile; 
 
 an enhancement unit, adapted to:
 generate a second histogram based on the second statistical distribution; and 
 generate a second image based on the first image and the second histogram. 
 
 
     
     
       12. The system of  claim 11 , wherein the cloud generator comprises multiple random number generators (RNGs) and multiple buffers, the RNGs generate random variables with Gaussian distribution, and the multiple buffers store the intermediate random values generated by the RNGs. 
     
     
       13. The system of  claim 11 , wherein the computing unit is further adapted to:
 use the first parameter profile as an input to the inverse cloud generator to generate a first statistical distribution; and 
 use the first distribution to perform the histogram specification to the first histogram of the first image. 
 
     
     
       14. The system of  claim 1 , wherein the computing unit is further adapted to:
 use the second parameter profile as an input to the cloud generator to generate the second statistical distribution. 
 
     
     
       15. The system of  claim 11 , the image processing system further comprising an input unit, to calculate the first parameter profile from the first image,
 the input unit is adapted to read the first image and storing intensity information for each pixel of the first image; and 
 the computing unit is adapted to calculate the first parameter profile according to the stored intensity information. 
 
     
     
       16. The system of  claim 15 , wherein the intensity information includes at least one of RGB values in a RGB format image, Y-component values in a YUV format image, or grey level values in a grayscale image. 
     
     
       17. The system of  claim 11 , wherein the parameter profile includes at least one of an average luminance of the first image, brightness of the first image, or a contrast of the first image. 
     
     
       18. The system of  claim 13 , to generate the first statistical distribution based on the first parameter profile, the computing unit is adapted to:
 transfer the first parameter profile to the cloud generator; and 
 generate the first statistical distribution via the cloud generator mapping at least three parameters selected from the first parameter profile. 
 
     
     
       19. The system of  claim 18 , wherein the at least three parameters selected from the first parameter profile comprise expectation, entropy and hyper entropy. 
     
     
       20. The system of  claim 13 , to generate the second parameter profile by adjusting the first parameter profile, the computing unit is adapted to use an iterative algorithm.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.